Commit History
Explicitly set `weight_decay` value (#8592)
7204c1c
unverified
Update requirements.txt comment spacing (#8562)
72a81e7
unverified
Assert `--optimize` not used with cuda device (#8569)
f4b0568
unverified
Raise error on suffix-less model path (#8561)
f8722b4
unverified
Add `thop>=0.1.0` (#8558)
574ceed
unverified
Add TensorRT dependencies (#8553)
fbd3020
unverified
曾逸夫（Zeng Yifu）
commited on
Update metrics.py with IoU protected divides (#8550)
0414637
unverified
CIoU protected divides (#8546)
a84cd02
unverified
val.py `assert ncm == nc` fix (#8545)
7dafd1c
unverified
Fix `LoadImages()` with dataset YAML lists (#8517)
526e650
unverified
XML export `--half` fix (#8522)
c215e87
unverified
Add `--half` arguments to export.py Usage examples (#8516)
63ba0cb
unverified
Properly expose `batch_size` from OpenVINO similarly to TensorRT (#8514)
be42a24
unverified
Simplify benchmarks.py assertions (#8515)
f17444a
unverified
Add `--hard-fail` argument to benchmarks for CI errors (#8513)
3e54651
unverified
Fix AP calculation bug #8464 (#8484)
39d7a93
unverified
Avoid FP64 ops for MPS support in train.py (#8511)
dd28df9
unverified
Revert "Expose OpenVINO `batch_size` similarly to TensorRT" (#8510)
9d7bc06
unverified
Training reproducibility improvements (#8213)
27d831b
unverified
Update tutorial.ipynb (#8507)
36f64a9
unverified
Exclude torch==1.12.0, torchvision==0.13.0 (Fix #8395) (#8497)
1ab23fc
unverified
Junya Morioka
commited on
[pre-commit.ci] pre-commit suggestions (#8470)
fdc9d91
unverified
pre-commit-ci[bot]
pre-commit-ci[bot]
commited on
Update stale.yml (#8465)
c768919
unverified
Do not prefer Apple MPS (#8446)
29d79a6
unverified
Expose OpenVINO `batch_size` similarly to TensorRT (#8437)
da2ee39
unverified
TRT `--half` fix autocast images to FP16 (#8435)
d94b470
unverified
Update cache comments (#8414)
8983324
unverified
Improve `--local_rank` arg comment (#8409)
e50dc38
unverified
Implementation of Early Stopping for DDP training (#8345)
6935a54
unverified
Update tutorial.ipynb (#8380)
f76a78e
unverified
Fix ONNX `--dynamic` export on GPU (#8378)
0c13240
unverified
Update protobuf requirement from <=3.20.1 to <4.21.3 (#8346)
50ff6ee
unverified
Add File Size (MB) column to benchmarks (#8359)
34df503
unverified
Fix bias warmup LR init (#8356)
8ebf569
unverified
Revamp Chinese docs (#8350)
b0814c9
unverified
Allow detect.py to use video size for initial window size (#8330)
0537e8d
unverified
Create README_cn.md (#8344)
5c990e3
unverified
Allow preview resize in detect.py (#8318)
19f33cb
unverified
`device_name="MYRIAD" for Intel NCS2` comment (#8327)
724d5b2
unverified
`logging.ERROR` on `RANK` not in (0, 1) (#8284)
a2a1ed2
unverified
Created using Colaboratory (#8255)
1156a32
unverified
`process_batch()` as numpy arrays (#8254)
669f707
unverified
HUB dataset_stats() error reporting (#8192)
d605138
unverified
Prefer MPS over CPU if available (#8210)
303f378
unverified
Remove streaming source sleep period (#8243)
86e6add
unverified
Reject webcam inference on Colab/Kaggle (#8209)
75bbaa8
unverified
Bump actions/setup-python from 3 to 4 (#8186)
6a67594
unverified
dependabot[bot]
dependabot[bot]
commited on